agentmods.dev

llm-wiki: Command for Claude Code

.claude/commands/wiki-ingest.md

wiki-ingest is a command for Claude Code from Pratiyush/llm-wiki. It costs 0 tokens per session (451 once invoked), scanned A, original, MIT.

A command that turns source documents or folders into connected llmwiki pages, including pages about sources, people, companies, tools, and ideas.

In plain words
What is it for?
Use it to add files from a repository's raw folder to the wiki and update its overview, entity pages, concept pages, and change log.
Why use it?
It removes the manual work of reading documents, updating indexes, linking related information, and tracking conflicts.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

This is Pratiyush/llm-wiki's own configuration. It tells Claude Code how to work on llm-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki configures →

Part of the llm-wiki plugin — 6 skills, 18 commands shipped together

not rated 386repo +2 2mo ago A scan 0 tokens original MIT
View source ↗ Pratiyush/llm-wiki
Reuse

Borrowing it

Nothing to install: this file belongs to Pratiyush/llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Pratiyush/llm-wiki/master/.claude/commands/wiki-ingest.md
Clone the repo
git clone --depth 1 https://github.com/Pratiyush/llm-wiki

Made for: Claude Code.

Or install llm-wiki, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wiki-ingest

README.md
[![agentmods](https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-ingest.svg)](https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-ingest)
Your own site
<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00451
Opus 5 $0.00000 $0.00226
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 9d ago against content hash c6b2654ad9fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wiki-ingest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/wiki-ingest.md · 33 lines

What it actually says

Ingest a source document (or folder) into the llmwiki.

Usage: /wiki-ingest

$ARGUMENTS should be a path relative to the repo root — typically a file or folder under raw/. Examples:

  • /wiki-ingest raw/sessions/ai-newsletter/2026-04-04-kind-tinkering-hejlsberg.md
  • /wiki-ingest raw/sessions/ai-newsletter/
  • /wiki-ingest raw/sessions/

Follow the Ingest Workflow exactly as defined in CLAUDE.md:

  1. Read the source file (or every file in the folder) using the Read tool
  2. Read wiki/index.md and wiki/overview.md for current context
  3. Write wiki/sources/<slug>.md per the Source Page Format in CLAUDE.md
  4. Update wiki/index.md — add the new source under ## Sources
  5. Update wiki/overview.md if the source adds substantial new information
  6. Create or update wiki/entities/<Name>.md for any people, companies, projects, tools, libraries mentioned
  7. Create or update wiki/concepts/<Name>.md for any ideas, patterns, or frameworks discussed
  8. Cross-link everything with [[wikilinks]] under ## Connections
  9. Flag any contradictions with existing wiki content under ## Contradictions
  10. Append to wiki/log.md: ## [YYYY-MM-DD] ingest | <title>

If you are ingesting a session-derived source (a file under raw/sessions/), also apply the session-specific rules from CLAUDE.md §"Session-derived source specifics":

  • Trust the frontmatter as authoritative metadata
  • Do not copy the ## Conversation section verbatim
  • Create or update the project entity page
  • Extract any explicit decisions into wiki/concepts/
  • If there are more than ~20 files, ask the user before processing all of them

After finishing, summarise: what was added, which pages were created or updated, any contradictions found.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 33 lines · 0 tokens per session scan A c6b2654ad9fa

Subscribe to this mod's changes

wiki-ingest is a command published in the GitHub repository Pratiyush/llm-wiki (386 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 451 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeDocumentsResearchaicodex-clicursordeveloper-toolskarpathy
Related

Other commands, from other repositories

list

A command for listing documents distilled from the current project, such as reports, designs, incident records, books, and knowledge graphs. Distilled documents are shorter, structured records made from earlier work.

johnnywuj81/tokenknows · 27 tokens

extract-foundations-from-screens

Extract canonical foundations docs (foundations/color.md, foundations/typography.md, foundations/spacing.md, foundations/radii.md) from a batch of existing SCREENSPECs. Idempotent: re-runs only add new tokens, never overwrite existing role mappings, and route conflicts to a Review queue. Use when SCREENSPECs already…

Mozurok/fhorja.dev · 116 tokens

prompt-pilot

Rewrite a rough prompt into a precise, context-enriched prompt (read-only — never implements the task).

savasturkoglu1/promptpilot-plugin · 21 tokens

report-schema

Print or write markdown documentation for JSON report schema.

Leoyang183/sync-agents-settings · 12 tokens

sdd-apply

Implement SDD tasks — writes code following specs and design.

Gentleman-Programming/gentle-ai · 11 tokens

sdd-init

Initialize SDD context — detects project stack and bootstraps persistence backend.

Gentleman-Programming/gentle-ai · 14 tokens